Back to skill

Security audit

Cursor Prd Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown-only helper for turning small feature ideas into a PRD and Cursor rules snippet, with no evidence of hidden execution, data access, or persistence beyond user-copied output.

Install this if you want a Chinese-language PRD helper for small Cursor implementation specs. Review the generated .cursor/rules text before copying it into a project, because those rules can influence future Cursor agent behavior in that project.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad enough to match common product-discussion requests such as '帮我写 PRD' or '我想做一个功能', which can cause the skill to activate outside its intended narrow context. Over-broad activation can override a more appropriate skill, steer users into this workflow unnecessarily, and produce unintended files or guidance based on incomplete context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Forcing Simplified Chinese output regardless of user preference reduces user control and can cause the agent to ignore the user's explicit language choice or project requirements. In multi-user or mixed-language environments, this can lead to misunderstandings, unusable artifacts, or accidental policy mismatch, though it is not a direct code-execution or data-exfiltration issue.

Content

No source excerpt is available for this finding.